yaojingang/geohub · Archived
Route GEO and generative engine optimization requests to an available GEOHub capability.
This repository is archived — consider an actively maintained alternative.
Turn one natural-language request into an evidence-bounded SEO work plan across technical SEO, …
2 installsMeasure GEO visibility from an approved, file-backed engine observation bundle.
2 installsDiscover evidence-aware GEO questions, query rewrites, intent clusters, and prioritized content…
2 installsDiagnose a brand, website, or page for evidence-backed GEO gaps and opportunities from user-sup…
2 installsRelated neighbors and high-traction skills in the same topics — useful to compare before installing.
Helps users discover and install agent skills when they ask questions like "how do I do X", "fi…
3.3M installsBrowser automation CLI for AI agents. Use when the user needs to interact with websites, includ…
810.4K installsReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "chec…
617.3K installsBuild, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and …
576.5K installsPrepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Te…
568.3K installsOther skills from yaojingang/geohub.
npx skills add yaojingang/geohub
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
main
Files included with this skill beyond the listing page.
SKILL.md
1,454 B
SUMMARY.md
321 B
references/routing-contract.md and the suite resolver contract at ../RESOLVER.md.python3 scripts/runroute.py --text "<request>" or python -m geoseo_hub route --text "<request>". Add --lexical-only for the deterministic baseline or --plan-output <path> to compile a TaskPlan.decision.type is single_skill or workflow, runnable is true, and the selected Skill has a non-null entry.clarify, abstain, pending-implementation, or planned, preserve the reported reason, alternatives, required inputs, and execution boundary.Return the selected skill ID, lifecycle status, runnable flag, reason, entry path, suggestion, typed decision object, and optional stable workflow DAG. When requested, write a validated TaskPlan with its digest and status.
This skill selects and plans capabilities. Workflow execution requires an explicit TaskPlan, file-backed input map, bounded output root, and every declared approval or external-evidence gate. It does not simulate unavailable stages.